Auto Router

Model details

Model: openrouter/auto
Provider: openrouter
API: openai-completions
Base URL: https://openrouter.ai/api/v1
Input: text, image
Reasoning: Yes
Context window: 2,000,000
Max tokens: 4,096

Show configuration

{
  "providers": {
    "openrouter": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "openrouter/auto",
          "name": "Auto Router",
          "reasoning": true,
          "input": [
            "text",
            "image"
          ],
          "contextWindow": 2000000,
          "maxTokens": 4096,
          "cost": {
            "input": -1000000,
            "output": -1000000,
            "cacheRead": 0,
            "cacheWrite": 0
          },
          "compat": {
            "supportsDeveloperRole": false,
            "thinkingFormat": "openrouter"
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://openrouter.ai/api/v1"
    }
  }
}

Pricing

Pricing varies because this route chooses one or more underlying models at request time. Charges use the selected models' rates.

Session cost calculator

A session estimate is unavailable because this model does not have fixed token prices.

Compatibility flags

Effective values after applying Pi's API defaults and model overrides.

Effective compatibility flags for Auto Router
Feature	Value
`supportsStore`	Yes
`supportsDeveloperRole`	No
`supportsReasoningEffort`	Yes
`supportsUsageInStreaming`	Yes
`maxTokensField`	`max_completion_tokens`
`requiresToolResultName`	No
`requiresAssistantAfterToolResult`	No
`requiresThinkingAsText`	No
`requiresReasoningContentOnAssistantMessages`	No
`thinkingFormat`	`openrouter`
`openRouterRouting`	`Empty`
`vercelGatewayRouting`	`Empty`
`chatTemplateKwargs`	`Empty`
`zaiToolStream`	No
`supportsStrictMode`	Yes
`cacheControlFormat`	None
`sendSessionAffinityHeaders`	No
`supportsLongCacheRetention`	Yes

Also available from other providers